Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: merged_grok_data_mcp_1
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 

adapter_config.json

@@ -25,12 +25,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj",
     "k_proj",
     "v_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
     "up_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4973feca0fb8ac743580e90ae188baeec1515f4206f53b66fe4f3dc258612bdf
+oid sha256:bb14f0876d77ba677f291b13404a96c65dde13092462fc2732d490cec062f96c
 size 15220968

runs/Aug19_00-04-59_Pranaya.local/events.out.tfevents.1755583500.Pranaya.local.53378.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99b7a0eb5b73b82418727b5b2064b7dc2221137618514efbf8a31296acfde4a
+size 7909

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e569f9d7ca51e442d7b6d845429da0e1fe12a57db68d3661f39af32bef3bf36
+oid sha256:b80221ecebdeb613a0cab66830a736061e16a4dc6e03a0e5e57f610a68e211ee
 size 6225